{"id":"https://openalex.org/W4313484812","doi":"https://doi.org/10.1109/lars/sbr/wre56824.2022.9995835","title":"Application of Reinforcement Learning to The Orientation and Position Control of A 6 Degrees of Freedom Robotic Manipulator","display_name":"Application of Reinforcement Learning to The Orientation and Position Control of A 6 Degrees of Freedom Robotic Manipulator","publication_year":2022,"publication_date":"2022-10-18","ids":{"openalex":"https://openalex.org/W4313484812","doi":"https://doi.org/10.1109/lars/sbr/wre56824.2022.9995835"},"language":"en","primary_location":{"id":"doi:10.1109/lars/sbr/wre56824.2022.9995835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lars/sbr/wre56824.2022.9995835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Latin American Robotics Symposium (LARS), 2022 Brazilian Symposium on Robotics (SBR), and 2022 Workshop on Robotics in Education (WRE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045731054","display_name":"Felipe Rigueira Campos","orcid":null},"institutions":[{"id":"https://openalex.org/I10824318","display_name":"Universidade Federal de Ouro Preto","ror":"https://ror.org/056s65p46","country_code":"BR","type":"education","lineage":["https://openalex.org/I10824318"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Felipe Rigueira Campos","raw_affiliation_strings":["Universidade Federal de Ouro Preto e Instituto Tecnol&#x00F3;gico Vale,Programa de P&#x00F3;s-Gradua&#x00E7;&#x00E3;o em Instrumenta&#x00E7;&#x00E3;o, Controle e Automa&#x00E7;&#x00E3;o de Processos de Minera&#x00E7;&#x00E3;o,Ouro Preto,MG,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Ouro Preto e Instituto Tecnol&#x00F3;gico Vale,Programa de P&#x00F3;s-Gradua&#x00E7;&#x00E3;o em Instrumenta&#x00E7;&#x00E3;o, Controle e Automa&#x00E7;&#x00E3;o de Processos de Minera&#x00E7;&#x00E3;o,Ouro Preto,MG,Brazil","institution_ids":["https://openalex.org/I10824318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053557410","display_name":"Aline Xavier Fid\u00eancio","orcid":"https://orcid.org/0009-0003-0541-8895"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Aline Xavier Fidencio","raw_affiliation_strings":["Ruhr-University,Faculty of Electrical Engineering and Information Technology,Bochum,Germany","Faculty of Electrical Engineering and Information Technology, Ruhr-University, Bochum, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ruhr-University,Faculty of Electrical Engineering and Information Technology,Bochum,Germany","institution_ids":["https://openalex.org/I904495901"]},{"raw_affiliation_string":"Faculty of Electrical Engineering and Information Technology, Ruhr-University, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014219700","display_name":"Jac\u00f3 Dias Domingues","orcid":"https://orcid.org/0000-0003-1761-6234"},"institutions":[{"id":"https://openalex.org/I10824318","display_name":"Universidade Federal de Ouro Preto","ror":"https://ror.org/056s65p46","country_code":"BR","type":"education","lineage":["https://openalex.org/I10824318"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Jaco Domingues","raw_affiliation_strings":["Universidade Federal de Ouro Preto e Instituto Tecnol&#x00F3;gico Vale,Programa de P&#x00F3;s-Gradua&#x00E7;&#x00E3;o em Instrumenta&#x00E7;&#x00E3;o, Controle e Automa&#x00E7;&#x00E3;o de Processos de Minera&#x00E7;&#x00E3;o,Ouro Preto,MG,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Ouro Preto e Instituto Tecnol&#x00F3;gico Vale,Programa de P&#x00F3;s-Gradua&#x00E7;&#x00E3;o em Instrumenta&#x00E7;&#x00E3;o, Controle e Automa&#x00E7;&#x00E3;o de Processos de Minera&#x00E7;&#x00E3;o,Ouro Preto,MG,Brazil","institution_ids":["https://openalex.org/I10824318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000558559","display_name":"Gustavo Pessin","orcid":"https://orcid.org/0000-0002-7411-9229"},"institutions":[{"id":"https://openalex.org/I10824318","display_name":"Universidade Federal de Ouro Preto","ror":"https://ror.org/056s65p46","country_code":"BR","type":"education","lineage":["https://openalex.org/I10824318"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Gustavo Pessin","raw_affiliation_strings":["Universidade Federal de Ouro Preto e Instituto Tecnol&#x00F3;gico Vale,Programa de P&#x00F3;s-Gradua&#x00E7;&#x00E3;o em Instrumenta&#x00E7;&#x00E3;o, Controle e Automa&#x00E7;&#x00E3;o de Processos de Minera&#x00E7;&#x00E3;o,Ouro Preto,MG,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Ouro Preto e Instituto Tecnol&#x00F3;gico Vale,Programa de P&#x00F3;s-Gradua&#x00E7;&#x00E3;o em Instrumenta&#x00E7;&#x00E3;o, Controle e Automa&#x00E7;&#x00E3;o de Processos de Minera&#x00E7;&#x00E3;o,Ouro Preto,MG,Brazil","institution_ids":["https://openalex.org/I10824318"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034989154","display_name":"Gustavo Freitas","orcid":"https://orcid.org/0000-0001-5343-7028"},"institutions":[{"id":"https://openalex.org/I10824318","display_name":"Universidade Federal de Ouro Preto","ror":"https://ror.org/056s65p46","country_code":"BR","type":"education","lineage":["https://openalex.org/I10824318"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Gustavo Freitas","raw_affiliation_strings":["Universidade Federal de Ouro Preto e Instituto Tecnol&#x00F3;gico Vale,Programa de P&#x00F3;s-Gradua&#x00E7;&#x00E3;o em Instrumenta&#x00E7;&#x00E3;o, Controle e Automa&#x00E7;&#x00E3;o de Processos de Minera&#x00E7;&#x00E3;o,Ouro Preto,MG,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Ouro Preto e Instituto Tecnol&#x00F3;gico Vale,Programa de P&#x00F3;s-Gradua&#x00E7;&#x00E3;o em Instrumenta&#x00E7;&#x00E3;o, Controle e Automa&#x00E7;&#x00E3;o de Processos de Minera&#x00E7;&#x00E3;o,Ouro Preto,MG,Brazil","institution_ids":["https://openalex.org/I10824318"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5549,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73304523,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9807000160217285,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.890625536441803},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.693793773651123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6839752793312073},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.646950900554657},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5810551643371582},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.5316168665885925},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4917934238910675},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.47895175218582153},{"id":"https://openalex.org/keywords/robot-manipulator","display_name":"Robot manipulator","score":0.4541267454624176},{"id":"https://openalex.org/keywords/degrees-of-freedom","display_name":"Degrees of freedom (physics and chemistry)","score":0.4531335234642029},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4347139298915863},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.42400646209716797},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3387172818183899},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1571335792541504},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13484030961990356},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11418184638023376}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.890625536441803},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.693793773651123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6839752793312073},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.646950900554657},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5810551643371582},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.5316168665885925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4917934238910675},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.47895175218582153},{"id":"https://openalex.org/C2985527887","wikidata":"https://www.wikidata.org/wiki/Q1587588","display_name":"Robot manipulator","level":3,"score":0.4541267454624176},{"id":"https://openalex.org/C208081375","wikidata":"https://www.wikidata.org/wiki/Q274502","display_name":"Degrees of freedom (physics and chemistry)","level":2,"score":0.4531335234642029},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4347139298915863},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.42400646209716797},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3387172818183899},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1571335792541504},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13484030961990356},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11418184638023376},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lars/sbr/wre56824.2022.9995835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lars/sbr/wre56824.2022.9995835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Latin American Robotics Symposium (LARS), 2022 Brazilian Symposium on Robotics (SBR), and 2022 Workshop on Robotics in Education (WRE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W169931978","https://openalex.org/W583777665","https://openalex.org/W2126050029","https://openalex.org/W2736601468","https://openalex.org/W2891816981","https://openalex.org/W2911426134","https://openalex.org/W2954718200","https://openalex.org/W3120214316","https://openalex.org/W3136821044","https://openalex.org/W3137974035","https://openalex.org/W3162902697","https://openalex.org/W4214717370","https://openalex.org/W4287780908","https://openalex.org/W6684205842","https://openalex.org/W6764769363","https://openalex.org/W6776355998","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Applications":[0],"with":[1],"autonomous":[2],"robots":[3],"play":[4],"an":[5],"important":[6],"role":[7],"in":[8,12,35,54,122,160],"the":[9,17,27,47,71,76,84,115,127,130,141,153,157],"industry":[10],"and":[11,21,37,95,102],"everyday":[13],"life.":[14],"Among":[15],"them,":[16],"activities":[18,34],"of":[19,30,86,105,129],"manipulating":[20],"moving":[22],"objects":[23],"are":[24],"highlighted":[25],"by":[26,46,74],"wide":[28],"variety":[29],"possible":[31],"applications.":[32],"These":[33],"static":[36],"known":[38],"environments":[39],"can":[40,145],"be":[41],"implemented":[42],"through":[43],"logic":[44],"planned":[45],"developer,":[48],"but":[49,125,150],"this":[50],"is":[51],"not":[52,135],"feasible":[53],"dynamic":[55],"environments.":[56],"Machine":[57],"Learning":[58,64],"(ML)":[59],"techniques":[60],"such":[61],"as":[62],"Reinforcement":[63],"(RL)":[65],"algorithms":[66],"have":[67,117],"sought":[68],"to":[69,79,156,162],"replace":[70],"pre-defined":[72],"programming":[73],"teaching":[75],"robot":[77],"how":[78],"act.":[80],"This":[81],"paper":[82],"presents":[83],"implementation":[85],"two":[87],"RL":[88],"algorithms,":[89],"Deep":[90],"Deterministic":[91],"Policy":[92,97],"Gradient":[93],"(DDPG)":[94],"Proximal":[96],"Optimization":[98],"(PPO),":[99],"for":[100],"orientation":[101],"position":[103],"control":[104],"a":[106,118,137],"6-degree-of-freedom":[107],"(6-DoF)":[108],"robotic":[109],"manipulator.":[110],"The":[111],"results":[112],"demonstrated":[113],"that":[114],"DDPG":[116],"faster":[119],"learning":[120,164],"convergence":[121,154],"simpler":[123],"activities,":[124],"if":[126],"complexity":[128],"problem":[131],"increases,":[132],"it":[133,151],"might":[134],"obtain":[136],"satisfactory":[138],"behavior.":[139],"On":[140],"other":[142],"hand,":[143],"PPO":[144],"solve":[146],"more":[147],"complex":[148],"problems":[149],"limits":[152],"rate":[155],"best":[158],"result":[159],"order":[161],"avoid":[163],"instability.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
